maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/llvm.memcpy.ll

373 lines
12 KiB
LLVM
Raw Normal View History

AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior This should really be true for any immediate, not just inline ones. llvm-svn: 277260
2016-07-30 09:40:36 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
Enable FeatureFlatForGlobal on Volcanic Islands This switches to the workaround that HSA defaults to for the mesa path. This should be applied to the 4.0 branch. Patch by Vedran Miletić <vedran@miletic.net> llvm-svn: 292982
2017-01-25 06:02:15 +08:00
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
declare void @llvm.memcpy.p3i8.p3i8.i32(i8 addrspace(3)* nocapture, i8 addrspace(3)* nocapture, i32, i32, i1) nounwind
declare void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(1)* nocapture, i64, i32, i1) nounwind
AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior This should really be true for any immediate, not just inline ones. llvm-svn: 277260
2016-07-30 09:40:36 +08:00
declare void @llvm.memcpy.p1i8.p2i8.i64(i8 addrspace(1)* nocapture, i8 addrspace(2)* nocapture, i64, i32, i1) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_lds_to_lds_align1:
AMDGPU/SI: Improve MachineSchedModel definition This patch contains a few improvements to the model, including: - Using a single resource with a defined buffers size for each memory unit. - Setting the IssueWidth correctly. - Fixing latency values for memory instructions. shader-db stats: 16429 shaders in 3231 tests Totals: SGPRS: 318232 -> 312328 (-1.86 %) VGPRS: 208996 -> 209346 (0.17 %) Code Size: 7147044 -> 7166440 (0.27 %) bytes LDS: 83 -> 83 (0.00 %) blocks Scratch: 1862656 -> 1459200 (-21.66 %) bytes per wave Max Waves: 49182 -> 49243 (0.12 %) Wait states: 0 -> 0 (0.00 %)A Differential Revision: http://reviews.llvm.org/D18453 llvm-svn: 264877
2016-03-31 00:35:13 +08:00
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_read_u8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
; SI-DAG: ds_write_b8
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_lds_to_lds_align1(i64 addrspace(3)* noalias %out, i64 addrspace(3)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(3)* %in to i8 addrspace(3)*
%bcout = bitcast i64 addrspace(3)* %out to i8 addrspace(3)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p3i8.p3i8.i32(i8 addrspace(3)* %bcout, i8 addrspace(3)* %bcin, i32 32, i32 1, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_lds_to_lds_align2:
AMDGPU/SI: Improve MachineSchedModel definition This patch contains a few improvements to the model, including: - Using a single resource with a defined buffers size for each memory unit. - Setting the IssueWidth correctly. - Fixing latency values for memory instructions. shader-db stats: 16429 shaders in 3231 tests Totals: SGPRS: 318232 -> 312328 (-1.86 %) VGPRS: 208996 -> 209346 (0.17 %) Code Size: 7147044 -> 7166440 (0.27 %) bytes LDS: 83 -> 83 (0.00 %) blocks Scratch: 1862656 -> 1459200 (-21.66 %) bytes per wave Max Waves: 49182 -> 49243 (0.12 %) Wait states: 0 -> 0 (0.00 %)A Differential Revision: http://reviews.llvm.org/D18453 llvm-svn: 264877
2016-03-31 00:35:13 +08:00
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_read_u16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
; SI-DAG: ds_write_b16
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_lds_to_lds_align2(i64 addrspace(3)* noalias %out, i64 addrspace(3)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(3)* %in to i8 addrspace(3)*
%bcout = bitcast i64 addrspace(3)* %out to i8 addrspace(3)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p3i8.p3i8.i32(i8 addrspace(3)* %bcout, i8 addrspace(3)* %bcin, i32 32, i32 2, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_lds_to_lds_align4:
AMDGPU: Split LDS vector loads If properly aligned this could allow using ds_read_b64. llvm-svn: 253975
2015-11-24 20:18:54 +08:00
; SI: ds_read2_b32
; SI: ds_read2_b32
; SI: ds_read2_b32
; SI: ds_read2_b32
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
AMDGPU: Split LDS vector loads If properly aligned this could allow using ds_read_b64. llvm-svn: 253975
2015-11-24 20:18:54 +08:00
; SI: ds_write2_b32
; SI: ds_write2_b32
; SI: ds_write2_b32
; SI: ds_write2_b32
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_lds_to_lds_align4(i64 addrspace(3)* noalias %out, i64 addrspace(3)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(3)* %in to i8 addrspace(3)*
%bcout = bitcast i64 addrspace(3)* %out to i8 addrspace(3)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p3i8.p3i8.i32(i8 addrspace(3)* %bcout, i8 addrspace(3)* %bcin, i32 32, i32 4, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
; FIXME: Use 64-bit ops
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_lds_to_lds_align8:
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
AMDGPU/SI: Enable load-store-opt by default. Summary: Enable load-store-opt by default, and update LIT tests. Reviewers: arsenm Differential Revision: http://reviews.llvm.org/D20694 llvm-svn: 270894
2016-05-27 03:35:29 +08:00
; SI: ds_read2_b64
; SI: ds_read2_b64
; SI: ds_write2_b64
; SI: ds_write2_b64
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI-DAG: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_lds_to_lds_align8(i64 addrspace(3)* noalias %out, i64 addrspace(3)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(3)* %in to i8 addrspace(3)*
%bcout = bitcast i64 addrspace(3)* %out to i8 addrspace(3)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p3i8.p3i8.i32(i8 addrspace(3)* %bcout, i8 addrspace(3)* %bcin, i32 32, i32 8, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_global_to_global_align1:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI-DAG: buffer_load_ubyte
; SI-DAG: buffer_store_byte
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_global_to_global_align1(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(1)* %in to i8 addrspace(1)*
%bcout = bitcast i64 addrspace(1)* %out to i8 addrspace(1)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %bcout, i8 addrspace(1)* %bcin, i64 32, i32 1, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_global_to_global_align2:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_load_ushort
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI-DAG: buffer_store_short
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_global_to_global_align2(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(1)* %in to i8 addrspace(1)*
%bcout = bitcast i64 addrspace(1)* %out to i8 addrspace(1)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %bcout, i8 addrspace(1)* %bcin, i64 32, i32 2, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_global_to_global_align4:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: buffer_load_dwordx4
; SI: buffer_load_dwordx4
; SI: buffer_store_dwordx4
; SI: buffer_store_dwordx4
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_global_to_global_align4(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(1)* %in to i8 addrspace(1)*
%bcout = bitcast i64 addrspace(1)* %out to i8 addrspace(1)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %bcout, i8 addrspace(1)* %bcin, i64 32, i32 4, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_global_to_global_align8:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: buffer_load_dwordx4
; SI: buffer_load_dwordx4
; SI: buffer_store_dwordx4
; SI: buffer_store_dwordx4
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_global_to_global_align8(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(1)* %in to i8 addrspace(1)*
%bcout = bitcast i64 addrspace(1)* %out to i8 addrspace(1)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %bcout, i8 addrspace(1)* %bcin, i64 32, i32 8, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
R600: Call EmitFunctionHeader() in the AsmPrinter to populate the ELF symbol table llvm-svn: 218776
2014-10-02 01:15:17 +08:00
; FUNC-LABEL: {{^}}test_small_memcpy_i64_global_to_global_align16:
R600/SI: Change all instruction assembly names to lowercase. This matches the format produced by the AMD proprietary driver. //==================================================================// // Shell script for converting .ll test cases: (Pass the .ll files you want to convert to this script as arguments). //==================================================================// ; This was necessary on my system so that A-Z in sed would match only ; upper case. I'm not sure why. export LC_ALL='C' TEST_FILES="$*" MATCHES=`grep -v Patterns SIInstructions.td | grep -o '"[A-Z0-9_]\+["e]' | grep -o '[A-Z0-9_]\+' | sort -r` for f in $TEST_FILES; do # Check that there are SI tests: grep -q -e 'verde' -e 'bonaire' -e 'SI' -e 'tahiti' $f if [ $? -eq 0 ]; then for match in $MATCHES; do sed -i -e "s/\([ :]$match\)/\L\1/" $f done # Try to get check lines with partial instruction names sed -i 's/\(;[ ]*SI[A-Z\\-]*: \)\([A-Z_0-9]\+\)/\1\L\2/' $f fi done sed -i -e 's/bb0_1/BB0_1/g' ../../../test/CodeGen/R600/infinite-loop.ll sed -i -e 's/SI-NOT: bfe/SI-NOT: {{[^@]}}bfe/g'../../../test/CodeGen/R600/llvm.AMDGPU.bfe.*32.ll ../../../test/CodeGen/R600/sext-in-reg.ll sed -i -e 's/exp_IEEE/EXP_IEEE/g' ../../../test/CodeGen/R600/llvm.exp2.ll sed -i -e 's/numVgprs/NumVgprs/g' ../../../test/CodeGen/R600/register-count-comments.ll sed -i 's/\(; CHECK[-NOT]*: \)\([A-Z_0-9]\+\)/\1\L\2/' ../../../test/CodeGen/R600/select64.ll ../../../test/CodeGen/R600/sgpr-copy.ll //==================================================================// // Shell script for converting .td files (run this last) //==================================================================// export LC_ALL='C' sed -i -e '/Patterns/!s/\("[A-Z0-9_]\+[ "e]\)/\L\1/g' SIInstructions.td sed -i -e 's/"EXP/"exp/g' SIInstrInfo.td llvm-svn: 221350
2014-11-05 22:50:53 +08:00
; SI: buffer_load_dwordx4
; SI: buffer_load_dwordx4
; SI: buffer_store_dwordx4
; SI: buffer_store_dwordx4
; SI: s_endpgm
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_small_memcpy_i64_global_to_global_align16(i64 addrspace(1)* noalias %out, i64 addrspace(1)* noalias %in) nounwind {
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
%bcin = bitcast i64 addrspace(1)* %in to i8 addrspace(1)*
%bcout = bitcast i64 addrspace(1)* %out to i8 addrspace(1)*
Revert "Change memcpy/memset/memmove to have dest and source alignments." This reverts commit r253511. This likely broke the bots in http://lab.llvm.org:8011/builders/clang-ppc64-elf-linux2/builds/20202 http://bb.pgr.jp/builders/clang-3stage-i686-linux/builds/3787 llvm-svn: 253543
2015-11-19 13:56:52 +08:00
call void @llvm.memcpy.p1i8.p1i8.i64(i8 addrspace(1)* %bcout, i8 addrspace(1)* %bcin, i64 32, i32 16, i1 false) nounwind
R600/SI: Implement getOptimalMemOpType The default guess uses i32. This needs an address space argument to really do the right thing in all cases. llvm-svn: 214104
2014-07-29 01:49:26 +08:00
ret void
}
AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior This should really be true for any immediate, not just inline ones. llvm-svn: 277260
2016-07-30 09:40:36 +08:00
; Test shouldConvertConstantLoadToIntImm
@hello.align4 = private unnamed_addr addrspace(2) constant [16 x i8] c"constant string\00", align 4
@hello.align1 = private unnamed_addr addrspace(2) constant [16 x i8] c"constant string\00", align 1
; FUNC-LABEL: {{^}}test_memcpy_const_string_align4:
; SI: s_getpc_b64
[AMDGPU] Emit constant address space data in .rodata section and use relocations instead of fixups (amdhsa only) Differential Revision: https://reviews.llvm.org/D25693 llvm-svn: 284759
2016-10-21 02:12:38 +08:00
; SI: s_add_u32 s{{[0-9]+}}, s{{[0-9]+}}, hello.align4+20
AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior This should really be true for any immediate, not just inline ones. llvm-svn: 277260
2016-07-30 09:40:36 +08:00
; SI: s_addc_u32
[AMDGPU] Emit constant address space data in .rodata section and use relocations instead of fixups (amdhsa only) Differential Revision: https://reviews.llvm.org/D25693 llvm-svn: 284759
2016-10-21 02:12:38 +08:00
; SI-DAG: s_load_dwordx4
; SI-DAG: s_load_dwordx4
; SI-DAG: s_load_dwordx2
; SI-DAG: buffer_store_dwordx4
; SI-DAG: buffer_store_dwordx4
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_memcpy_const_string_align4(i8 addrspace(1)* noalias %out) nounwind {
AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior This should really be true for any immediate, not just inline ones. llvm-svn: 277260
2016-07-30 09:40:36 +08:00
%str = bitcast [16 x i8] addrspace(2)* @hello.align4 to i8 addrspace(2)*
call void @llvm.memcpy.p1i8.p2i8.i64(i8 addrspace(1)* %out, i8 addrspace(2)* %str, i64 32, i32 4, i1 false)
ret void
}
; FUNC-LABEL: {{^}}test_memcpy_const_string_align1:
; SI-NOT: buffer_load
; SI: v_mov_b32_e32 v{{[0-9]+}}, 0x69
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
; SI: buffer_store_byte
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_memcpy_const_string_align1(i8 addrspace(1)* noalias %out) nounwind {
AMDGPU: Fix shouldConvertConstantLoadToIntImm behavior This should really be true for any immediate, not just inline ones. llvm-svn: 277260
2016-07-30 09:40:36 +08:00
%str = bitcast [16 x i8] addrspace(2)* @hello.align1 to i8 addrspace(2)*
call void @llvm.memcpy.p1i8.p2i8.i64(i8 addrspace(1)* %out, i8 addrspace(2)* %str, i64 32, i32 1, i1 false)
ret void
}